Abstract: Implementations relate to generating multi-modal response(s) through utilization of large language model(s) (LLM(s)) and other generative model(s). Processor(s) of a system can: receive natural language (NL) based input, generate a multi-modal response that is responsive to the NL based output, and cause the multi-modal response to be rendered. In some implementations, and in generating the multi-modal response, the processor(s) can process, using a LLM, LLM input to generate LLM output, and determine, based on the LLM output, textual content and generative multimedia content for inclusion in the multi-modal response. In some implementations, the generative multimedia content can be generated by another generative model (e.g., an image generator, a video generator, an audio generator, etc.) based on generative multimedia content prompt(s) included in the LLM output and that is indicative of the generative multimedia content.

Abstract: A process includes determining, by a recommendation engine, a security risk profile for a container environment. The container environment includes a plurality of pods that are to be deployed on an infrastructure that includes a plurality of nodes. Determining the security risk profile includes determining an infrastructure context characterizing the infrastructure and determining a workload context characterizing a workload associated with the container environment. The process includes determining, by the recommendation engine, a recommendation of a security policy for the container environment based on the security risk profile. The security policy includes a security control. The process includes deploying an agent to the infrastructure to manage compliance of the container environment with the security control.

Abstract: Implementations relate to managing multimedia content that is obtained by large language model(s) (LLM(s)) and/or generated by other generative model(s). Processor(s) of a system can: receive natural language (NL) based input that requests multimedia content, generate a response that is responsive to the NL based input, and cause the response to be rendered. In some implementations, and in generating the response, the processor(s) can process, using a LLM, LLM input to generate LLM output, and determine, based on the LLM output, at least multimedia content to be included in the response. Further, the processor(s) can evaluate the multimedia content to determine whether it should be included in the response. In response to determining that the multimedia content should not be included in the response, the processor(s) can cause the response, including alternative multimedia content or other textual content, to be rendered.

Abstract: Embodiments herein describe tokenizing a data sequence to perform a wildcard lookup. For example, a network device (such as a NIC or a switch) can receive a data sequence (e.g., an IP address, Uniform Resource Locator (URL), domain name, etc.) which can be broken down into separate tokens. After identifying a first token, the network device can search a wildcard lookup table to determine a first entry in the table that matches the first token. Assuming there is a match, the network device can identify an action associated with the entry. If the action is to continue with the search, the network device can then retrieve a key from the entry which it then combines with a second token in the data sequence to again search the wildcard lookup table.

Abstract: Implementations relate to generating multi-modal response(s) through utilization of large language model(s) (LLM(s)). Processor(s) of a system can: receive natural language (NL) based input, generate a multi-modal response that is responsive to the NL based output, and cause the multi-modal response to be rendered. In some implementations, and in generating the multi-modal response, the processor(s) can process, using a LLM, LLM input (e.g., that includes at least the NL based input) to generate LLM output, and determine, based on the LLM output, textual content for inclusion in the multi-modal response and multimedia content for inclusion in the multi-modal response. In some implementations, the multimedia content can be obtained based on a multimedia content tag that is included in the LLM output and that is indicative of the multimedia content. In various implementations, the multimedia content can be interleaved between segments of the textual content.

Abstract: A connected car and an onboard user equipment (UE) may establish independent cellular connections and may also establish a connection between each other. The UE establishes a first cellular link between the UE and a first network, establishes a connection with a connected car, wherein the connected car has a second cellular link between the connected car and a second network, evaluates one or more conditions and declares one of the first cellular link or the connection with the connected car a primary network interface for the UE based on, at least, the one or more conditions.

Abstract: A method (100) for predicting a sepsis status of a patient using a sepsis analysis system (200) comprising: (i) receiving (120) demographic information about the patient; (ii) receiving (130) observation data from a patient monitoring device; (iii) receiving (140) one or more patient responses provided by the patient in response to one or more queries or commands posed to the patient by the sepsis analysis system, and wherein the one or more queries or commands are configured to elicit, in the one or more patient responses, information relevant to the patient's sepsis status; (iv) analyzing (150), by a trained patient sepsis status model of the sepsis analysis system, the received demographic information, the received observation data, and the one or more patient responses to predict a sepsis status for the patient; and (v) reporting (170), via a user interface of the sepsis analysis system, the predicted sepsis status.

Abstract: In one embodiment, a test process herein may: execute an application under test; monitor execution of the application under test for system calls specific to a particular operating system in which the application under test is being executed; capture a count of system calls specific to the particular operating system during the execution of the application under test; and compute a portability metric based on the count of system calls specific to the particular operating system, the portability metric indicative of how dependent the application under test is on the particular operating system.

Abstract: A process is provided for treating demineralized bone (DB) comprising incubating the DB with a solution of a chaotropic agent at a temperature in the range of about 12° C. to about 30° C. to increase the release of a bone growth factor followed by selectively removing the chaotropic agent while retaining the released growth factor and the DB. A product prepared by the process is also provided as is the use of said product to promote bone formation or bone fusion in a subject in need thereof.

Abstract: Generally, in one aspect a process for providing adaptive suggestions in the CPOE is provided. The process includes: (i) generating a rule set from historic patient data (ii) receiving data specific to a patient (iii) determining, by a processor of the adaptive suggestion system containing a set of created rules, the most likely entry for that component of the CPOE based on the rule set and received patient data (iv) displaying via user interface the suggested entry for the component of the CPOE.

Abstract: Examples disclosed herein relate to systems and methods for generating and implementing a security profile. Disclosed methods may include the steps of generating a customer intent interface configured to receive input comprising a value associated with an intent parameter; receiving, via the customer intent interface, security intent information comprising the value and the intent parameter; generating a configuration file based on the security intent information; based on the configuration file, generating a security profile for a target device; and generating, by code generator framework, one or more scripts based on the security profile.

Abstract: Systems and methods are provided for implementing an adaptive machine learning platform for security penetration and risk assessment. For example, the system can receive publicly-available information associated with a client computer system, process the information to identify an input feature, and implement a machine learning model to identify the corresponding risk associated with the input feature. The system can recommend a penetration test for discovered weaknesses associated with the input feature and help make changes to the client computer system to improve security and reduce riskoverall.

Abstract: Systems, apparatus, articles of manufacture, and methods are disclosed to manage network slices. An example apparatus includes interface circuitry to acquire network information, machine-readable instructions, and at least one processor circuit to be programmed by the machine-readable instructions to reserve first network slices to satisfy service level objectives (SLOs) corresponding to first nodes, reserve second network slices to satisfy SLOs corresponding to second nodes, and reconfigure the first network slices to accept network communications from the second nodes when the network communications from the second nodes exceed a performance metric threshold.

Abstract: Examples disclosed herein relate to performing a security action based on a comparison of digital signatures. An intrusion detection mode is initiated by a baseboard management controller. A first digital signature of hardware devices is calculated during the activation of the intrusion detection mode. The first digital signature is stored. Upon detection of a trigger, a second digital signature is calculated for the current hardware devices. The digital signatures are compared. A security action is performed based on the comparison.

Abstract: Systems and methods are provided for implementing an adaptive machine learning platform for security penetration and risk assessment. For example, the system can receive publicly-available information associated with a client computer system, process the information to identify an input feature, and implement a machine learning model to identify the corresponding risk associated with the input feature. The system can recommend a penetration test for discovered weaknesses associated with the input feature and help make changes to the client computer system to improve security and reduce risk overall.

Abstract: A method includes accessing an input representing a software component list for a software product. The software component list contains information for a given software component. The method includes accessing a knowledge base to determine security level parameters and trust parameters for the given software component based on the information. A security level of the given software component is determined based on an evaluation of the security level parameters. A trust of a source of the given software component is determined based on an evaluation of the trust parameters. The method includes determining a security context of the software product. Based on the security level, the trust and the security context, the method includes providing a recommendation for the given software component.

Abstract: Implementations relate to managing multimedia content that is obtained by large language model(s) (LLM(s)) and/or generated by other generative model(s). Processor(s) of a system can: receive natural language (NL) based input that requests multimedia content, generate a response that is responsive to the NL based input, and cause the response to be rendered. In some implementations, and in generating the response, the processor(s) can process, using a LLM, LLM input to generate LLM output, and determine, based on the LLM output, at least multimedia content to be included in the response. Further, the processor(s) can evaluate the multimedia content to determine whether it should be included in the response. In response to determining that the multimedia content should not be included in the response, the processor(s) can cause the response, including alternative multimedia content or other textual content, to be rendered.

Abstract: The present disclosure is directed to systems and methods for developing an individual-specific patient baseline for a target patient. An exemplary method involves: determining one or more acuity scores for the target patient; identifying patient health data corresponding to one or more low acuity time periods; storing retrospective clinical data from a group of patients in a second database; comparing the patient health data corresponding to the one or more low acuity time periods with retrospective clinical data from a group of patients by identifying one or more patient subgroups; determining the individual-specific patient baseline using an adaptive baseline selection algorithm, wherein the adaptive baseline selection algorithm is used to determine whether to determine the individual-specific patient baseline using patient health data or using retrospective clinical data from one or more patient subgroups; and displaying, using a user interface, the individual-specific patient baseline.

Abstract: Implementations relate to generating multi-modal response(s) through utilization of large language model(s) (LLM(s)). Processor(s) of a system can: receive natural language (NL) based input, generate a multi-modal response that is responsive to the NL based output, and cause the multi-modal response to be rendered. In some implementations, and in generating the multi-modal response, the processor(s) can process, using a LLM, LLM input (e.g., that includes at least the NL based input) to generate LLM output, and determine, based on the LLM output, textual content for inclusion in the multi-modal response and multimedia content for inclusion in the multi-modal response. In some implementations, the multimedia content can be obtained based on a multimedia content tag that is included in the LLM output and that is indicative of the multimedia content. In various implementations, the multimedia content can be interleaved between segments of the textual content.

Abstract: The present technology is directed to providing fault management with dynamic restricted access in a tenant network. The tenant network can be a private 5G cellular network or other wireless communication network. The present technology can identify a fault event within the tenant network based on received telemetry data, associate the fault event with a vendor component included in the tenant network, and generate a vendor fault context. The vendor fault context can be generated to include only the portion of telemetry data that is determined to be related to the fault event or the vendor component. The present technology can further use the vendor fault context to create a time-bound user account for remotely accessing the tenant network for fault triage and management. The time-bound user account can be associated to a static role-based access control (RBAC) scheme configured with access restrictions determined based on the vendor fault context.